Bio
My name is Joshua Levine. I'm a prompt engineer. AI systems are only as capable as the conversations they facilitate. The gap between what a system can do and what people actually use it for is an experience problem, not a capability problem. The second a user feels like the AI doesn't understand what they mean, not what they said but what they meant, the system stops being a tool and starts being an obstacle.
Before I was Head of Applied AI at Huzi, I built custom GPTs at the restaurant where I worked so wine servers could surface pairing recommendations mid-service. When I moved into real estate, I built research tools, objection-handling systems, and neighborhood analysis prompts. If the technology is there and nobody's using it well, I'll build the version that people actually want to interact with.
At Huzi, I reported directly to the CEO. I designed the prompt architecture for a configurable AI assistant platform: a modular system where platform behavior, assistant personality, coaching methodology, and task instructions each lived in their own layer with a single source of truth, so you could update one without breaking the others. I built and deployed AI coaching systems for enterprise clients in real estate, title, and financial services, turning their existing coaching methodologies into interactive conversational experiences.
Since Huzi, I've been shipping. I built a multi-agent publishing system that produces localized ebooks across ten languages. I designed and built Aloha, a personal AI assistant with persistent memory, a self-authoring identity architecture, and autonomous daily operations. The landscape in this field shifts constantly, and I care more about building a durable understanding of how these systems work than about nailing any particular setup. The only thing that ages well is the ability to evaluate what's actually happening and respond to it.